← All models
Claude Sonnet 4.6
★ featuredAnthropic · 14 recorded token offers
Top 5 cheapest providers (10:1 blended)
Within the active global provider, residency and confidentiality filters.
| # | Provider | Platform | Input/1M | Output/1M | Blended |
|---|---|---|---|---|---|
| 1 | Google Vertex AI | Google Vertex AI | $3.00 | $15.00 | $4.09 |
| 2 | Anthropic | Anthropic | $3.00 | $15.00 | $4.09 |
| 3 | Claude Platform on AWS | OpenRouter | $3.00 | $15.00 | $4.09 |
| 4 | Anthropic | OpenRouter | $3.00 | $15.00 | $4.09 |
| 5 | Amazon Bedrock | OpenRouter | $3.00 | $15.00 | $4.09 |
Benchmarks
Composite67.4
Mean-imputed base61.9
Dominance adjustment+5.5
Composite evidence3/5
AA Coding Index—
AA Coding Agent Index38.6
AA Intelligence Index—
DesignArena Frontend Elo1223
DesignArena Full-Stack Elo1237
LiveCodeBench—
SciCode—
Terminal-Bench Hard—
τ²-Bench (tool use)—
GPQA Diamond—
MMLU-Pro—
AA Math Index—
Output speed (t/s)—
ⓘ Intelligence.ai (formerly DesignArena) publishes this result at product/family scope without an effort setting. It is attached exactly once to claude-sonnet-4.6::medium, the deterministic family representative used by collapsed comparisons; this does not assert that Intelligence.ai tested this specific effort setting.
Variants / reasoning settings
| Variant | Coding | Intelligence | LiveCodeBench | Terminal-Bench |
|---|---|---|---|---|
| Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | 63.0 | 48.4 | — | 53.0% |
| Claude Sonnet 4.6 (Non-reasoning, Low Effort) | — | 35.1 | — | 42.4% |
| Claude Sonnet 4.6 (Non-reasoning, High Effort) | — | 36.8 | — | 46.2% |
| Sonnet 4.6 (medium) | — | — | — | — |
GitHub Copilot
Current usage-based billing · model token cost is converted to AI Credits at 1 credit = $0.01.
Input $3.00 / 1M
Cached input $0.300 / 1M
Cache write $3.75 / 1M
Output $15.00 / 1M
Status GA
Legacy annual Pro/Pro+ request billing only.
Multiplier 9.00×
Effective cost $0.360 / request
GitHub marks this multiplier as subject to change.
Token offers by platform
14 offers within the active global filters; “—” means the catalog is active but no public token price is available.
Google Vertex AI (2)
| Google Vertex AI | global | $3.00 in | $15.00 out | $4.09 |
| Google Vertex AI | europe-west1EU | $3.30 in | $16.50 out | $4.50 |
Anthropic (1)
| Anthropic | global | $3.00 in | $15.00 out | $4.09 |
OpenRouter (9)
| Claude Platform on AWS | globalclaude-on-aws | $3.00 in | $15.00 out | $4.09 |
| Anthropic | globalanthropic | $3.00 in | $15.00 out | $4.09 |
| Amazon Bedrock | globalamazon-bedrock/global | $3.00 in | $15.00 out | $4.09 |
| Azure | globalazure/global | $3.00 in | $15.00 out | $4.09 |
| globalgoogle-vertex/global | $3.00 in | $15.00 out | $4.09 | |
| Amazon Bedrock | globalamazon-bedrock/us | $3.30 in | $16.50 out | $4.50 |
| Amazon Bedrock | euamazon-bedrock/eu-west-1EU | $3.30 in | $16.50 out | $4.50 |
| globalgoogle-vertex/us-east5 | $3.30 in | $16.50 out | $4.50 | |
| eugoogle-vertex/europeEU | $3.30 in | $16.50 out | $4.50 |
AWS Bedrock (1)
| AWS Bedrock | eu-central-1 (EU cross-region inference profile)EU | $3.30 in | $16.50 out | $4.50 |
T-Systems LLM Hub (1)
| T-Systems LLM Hub | euEU | $3.47 in | $17.33 out | $4.73 |